This website requires JavaScript.
Explore
Help
Register
Sign In
ywkang
/
kernbench2
Watch
1
Star
0
Fork
0
You've already forked kernbench2
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
a98e93110b873815b4bff498972004261f957aeb
kernbench2
/
tests
/
attention
T
History
eusonice
f08dda3bd4
test short context length attention kernel
2026-06-26 15:59:21 -07:00
..
test_gqa_decode_long_ctx_composite.py
feat(gqa): Case-6 composite-command decode variants + on-chip-operand DMA fix
2026-06-23 16:07:41 -07:00
test_gqa_decode_opt2.py
perf(cost-model): D8 single-op-cmd fast-path (FIXED=8 single-op / 40 composite)
2026-06-17 15:04:53 -07:00
test_gqa_prefill_compute_bound.py
paper(gqa): two-regime "use of composite commands" — decode + compute-bound prefill
2026-06-23 17:04:26 -07:00
test_gqa_short_context_sweep_decode.py
test short context length attention kernel
2026-06-26 15:59:21 -07:00
test_gqa_short_context_sweep_prefill.py
test short context length attention kernel
2026-06-26 15:59:21 -07:00
test_gqa_short_context.py
test short context length attention kernel
2026-06-26 15:59:21 -07:00
test_milestone_gqa_decode_long_ctx_4cases.py
gqa: reorganize benches into gqa_helpers/ subpackage; drop legacy headline
2026-06-16 13:05:41 -07:00
test_milestone_gqa_prefill_long_ctx_4cases.py
gqa(prefill-4cases): add long-context prefill 4-cases comparative study
2026-06-16 13:06:08 -07:00